agent v0.85.0 WIP: F12/F11/F10/F9/F2/F1 boot-recovery plane + appliance self-heal (pre-build)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017CDMFpFx84pfviCTVuGGhf
2026-07-12 07:48:49 +02:00
parent bec4bac076
commit bc4eda926b
18 changed files with 1249 additions and 104 deletions
@@ -28,9 +28,14 @@ var SnippetPath = filepath.Join(SnippetDir, SnippetName)

 // snippetBody is the tiny wrapper PVE execs as `<script> <vmid> <phase>`. It delegates to the agent
 // binary so the heal LOGIC is the unit-tested Go, never duplicated (divergence-proof) shell. Executable.
+// The wrapper NEVER exec's and ALWAYS exits 0 (CAMPAIGN-3 F10/rc255 belt): a hook that exits nonzero
+// aborts the guest start. `exec` would surface the binary's exit code to PVE; instead we run it as a
+// child, swallow any nonzero (missing/crashed binary, OOM-kill), and `exit 0` unconditionally. The Go
+// side has its own recover + per-phase timeout — this is the second belt at the shell layer.
 const snippetBody = `#!/bin/sh
 # felhom-agent guest pre-start self-heal hook (C1 net). PVE calls: <script> <vmid> <phase>.
-exec ` + AgentBin + ` guest-hook "$1" "$2"
+` + AgentBin + ` guest-hook "$1" "$2" || true
+exit 0
 `

 // InstallSnippet writes the pre-start hook wrapper into the PVE snippets dir (idempotent, root-owned,